Merge tag 'net-5.10-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Networking fixes for 5.10-rc7, including fixes from bpf, netfilter,
  wireless drivers, wireless mesh and can.

  Current release - regressions:

   - mt76: usb: fix crash on device removal

  Current release - always broken:

   - xsk: Fix umem cleanup from wrong context in socket destruct

  Previous release - regressions:

   - net: ip6_gre: set dev->hard_header_len when using header_ops

   - ipv4: Fix TOS mask in inet_rtm_getroute()

   - net, xsk: Avoid taking multiple skbuff references

  Previous release - always broken:

   - net/x25: prevent a couple of overflows

   - netfilter: ipset: prevent uninit-value in hash_ip6_add

   - geneve: pull IP header before ECN decapsulation

   - mpls: ensure LSE is pullable in TC and openvswitch paths

   - vxlan: respect needed_headroom of lower device

   - batman-adv: Consider fragmentation for needed packet headroom

   - can: drivers: don't count arbitration loss as an error

   - netfilter: bridge: reset skb->pkt_type after POST_ROUTING traversal

   - inet_ecn: Fix endianness of checksum update when setting ECT(1)

   - ibmvnic: fix various corner cases around reset handling

   - net/mlx5: fix rejecting unsupported Connect-X6DX SW steering

   - net/mlx5: Enforce HW TX csum offload with kTLS"

* tag 'net-5.10-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (62 commits)
  net/mlx5: DR, Proper handling of unsupported Connect-X6DX SW steering
  net/mlx5e: kTLS, Enforce HW TX csum offload with kTLS
  net: mlx5e: fix fs_tcp.c build when IPV6 is not enabled
  net/mlx5: Fix wrong address reclaim when command interface is down
  net/sched: act_mpls: ensure LSE is pullable before reading it
  net: openvswitch: ensure LSE is pullable before reading it
  net: skbuff: ensure LSE is pullable before decrementing the MPLS ttl
  net: mvpp2: Fix error return code in mvpp2_open()
  chelsio/chtls: fix a double free in chtls_setkey()
  rtw88: debug: Fix uninitialized memory in debugfs code
  vxlan: fix error return code in __vxlan_dev_create()
  net: pasemi: fix error return code in pasemi_mac_open()
  cxgb3: fix error return code in t3_sge_alloc_qset()
  net/x25: prevent a couple of overflows
  dpaa_eth: copy timestamp fields to new skb in A-050385 workaround
  net: ip6_gre: set dev->hard_header_len when using header_ops
  mt76: usb: fix crash on device removal
  iwlwifi: pcie: add some missing entries for AX210
  iwlwifi: pcie: invert values of NO_160 device config entries
  iwlwifi: pcie: add one missing entry for AX210
  ...

1 files changed, 122 insertions, 68 deletions

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 2491ebc97871..da9450f18717 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -834,7 +834,7 @@ static void release_napi(struct ibmvnic_adapter *adapter)
 static int ibmvnic_login(struct net_device *netdev)
 {
 	struct ibmvnic_adapter *adapter = netdev_priv(netdev);
-	unsigned long timeout = msecs_to_jiffies(30000);
+	unsigned long timeout = msecs_to_jiffies(20000);
 	int retry_count = 0;
 	int retries = 10;
 	bool retry;
@@ -850,10 +850,8 @@ static int ibmvnic_login(struct net_device *netdev)
 		adapter->init_done_rc = 0;
 		reinit_completion(&adapter->init_done);
 		rc = send_login(adapter);
-		if (rc) {
-			netdev_warn(netdev, "Unable to login\n");
+		if (rc)
 			return rc;
-		}
 
 		if (!wait_for_completion_timeout(&adapter->init_done,
 						 timeout)) {
@@ -940,7 +938,7 @@ static void release_resources(struct ibmvnic_adapter *adapter)
 static int set_link_state(struct ibmvnic_adapter *adapter, u8 link_state)
 {
 	struct net_device *netdev = adapter->netdev;
-	unsigned long timeout = msecs_to_jiffies(30000);
+	unsigned long timeout = msecs_to_jiffies(20000);
 	union ibmvnic_crq crq;
 	bool resend;
 	int rc;
@@ -1857,7 +1855,7 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter,
 	if (reset_state == VNIC_OPEN) {
 		rc = __ibmvnic_close(netdev);
 		if (rc)
-			return rc;
+			goto out;
 	}
 
 	release_resources(adapter);
@@ -1875,24 +1873,25 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter,
 	}
 
 	rc = ibmvnic_reset_init(adapter, true);
-	if (rc)
-		return IBMVNIC_INIT_FAILED;
+	if (rc) {
+		rc = IBMVNIC_INIT_FAILED;
+		goto out;
+	}
 
 	/* If the adapter was in PROBE state prior to the reset,
 	 * exit here.
 	 */
 	if (reset_state == VNIC_PROBED)
-		return 0;
+		goto out;
 
 	rc = ibmvnic_login(netdev);
 	if (rc) {
-		adapter->state = reset_state;
-		return rc;
+		goto out;
 	}
 
 	rc = init_resources(adapter);
 	if (rc)
-		return rc;
+		goto out;
 
 	ibmvnic_disable_irqs(adapter);
 
@@ -1902,8 +1901,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter,
 		return 0;
 
 	rc = __ibmvnic_open(netdev);
-	if (rc)
-		return IBMVNIC_OPEN_FAILED;
+	if (rc) {
+		rc = IBMVNIC_OPEN_FAILED;
+		goto out;
+	}
 
 	/* refresh device's multicast list */
 	ibmvnic_set_multi(netdev);
@@ -1912,7 +1913,10 @@ static int do_change_param_reset(struct ibmvnic_adapter *adapter,
 	for (i = 0; i < adapter->req_rx_queues; i++)
 		napi_schedule(&adapter->napi[i]);
 
-	return 0;
+out:
+	if (rc)
+		adapter->state = reset_state;
+	return rc;
 }
 
 /**
@@ -2015,7 +2019,6 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 		rc = ibmvnic_login(netdev);
 		if (rc) {
-			adapter->state = reset_state;
 			goto out;
 		}
 
@@ -2083,6 +2086,9 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 	rc = 0;
 
 out:
+	/* restore the adapter state if reset failed */
+	if (rc)
+		adapter->state = reset_state;
 	rtnl_unlock();
 
 	return rc;
@@ -2115,43 +2121,46 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	if (rc) {
 		netdev_err(adapter->netdev,
 			   "Couldn't initialize crq. rc=%d\n", rc);
-		return rc;
+		goto out;
 	}
 
 	rc = ibmvnic_reset_init(adapter, false);
 	if (rc)
-		return rc;
+		goto out;
 
 	/* If the adapter was in PROBE state prior to the reset,
 	 * exit here.
 	 */
 	if (reset_state == VNIC_PROBED)
-		return 0;
+		goto out;
 
 	rc = ibmvnic_login(netdev);
-	if (rc) {
-		adapter->state = VNIC_PROBED;
-		return 0;
-	}
+	if (rc)
+		goto out;
 
 	rc = init_resources(adapter);
 	if (rc)
-		return rc;
+		goto out;
 
 	ibmvnic_disable_irqs(adapter);
 	adapter->state = VNIC_CLOSED;
 
 	if (reset_state == VNIC_CLOSED)
-		return 0;
+		goto out;
 
 	rc = __ibmvnic_open(netdev);
-	if (rc)
-		return IBMVNIC_OPEN_FAILED;
+	if (rc) {
+		rc = IBMVNIC_OPEN_FAILED;
+		goto out;
+	}
 
 	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, netdev);
 	call_netdevice_notifiers(NETDEV_RESEND_IGMP, netdev);
-
-	return 0;
+out:
+	/* restore adapter state if reset failed */
+	if (rc)
+		adapter->state = reset_state;
+	return rc;
 }
 
 static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
@@ -2173,17 +2182,6 @@ static struct ibmvnic_rwi *get_next_rwi(struct ibmvnic_adapter *adapter)
 	return rwi;
 }
 
-static void free_all_rwi(struct ibmvnic_adapter *adapter)
-{
-	struct ibmvnic_rwi *rwi;
-
-	rwi = get_next_rwi(adapter);
-	while (rwi) {
-		kfree(rwi);
-		rwi = get_next_rwi(adapter);
-	}
-}
-
 static void __ibmvnic_reset(struct work_struct *work)
 {
 	struct ibmvnic_rwi *rwi;
@@ -2241,20 +2239,23 @@ static void __ibmvnic_reset(struct work_struct *work)
 				rc = do_hard_reset(adapter, rwi, reset_state);
 				rtnl_unlock();
 			}
+			if (rc) {
+				/* give backing device time to settle down */
+				netdev_dbg(adapter->netdev,
+					   "[S:%d] Hard reset failed, waiting 60 secs\n",
+					   adapter->state);
+				set_current_state(TASK_UNINTERRUPTIBLE);
+				schedule_timeout(60 * HZ);
+			}
 		} else if (!(rwi->reset_reason == VNIC_RESET_FATAL &&
 				adapter->from_passive_init)) {
 			rc = do_reset(adapter, rwi, reset_state);
 		}
 		kfree(rwi);
-		if (rc == IBMVNIC_OPEN_FAILED) {
-			if (list_empty(&adapter->rwi_list))
-				adapter->state = VNIC_CLOSED;
-			else
-				adapter->state = reset_state;
-			rc = 0;
-		} else if (rc && rc != IBMVNIC_INIT_FAILED &&
-		    !adapter->force_reset_recovery)
-			break;
+		adapter->last_reset_time = jiffies;
+
+		if (rc)
+			netdev_dbg(adapter->netdev, "Reset failed, rc=%d\n", rc);
 
 		rwi = get_next_rwi(adapter);
 
@@ -2268,11 +2269,6 @@ static void __ibmvnic_reset(struct work_struct *work)
 		complete(&adapter->reset_done);
 	}
 
-	if (rc) {
-		netdev_dbg(adapter->netdev, "Reset failed\n");
-		free_all_rwi(adapter);
-	}
-
 	clear_bit_unlock(0, &adapter->resetting);
 }
 
@@ -2360,7 +2356,13 @@ static void ibmvnic_tx_timeout(struct net_device *dev, unsigned int txqueue)
 			   "Adapter is resetting, skip timeout reset\n");
 		return;
 	}
-
+	/* No queuing up reset until at least 5 seconds (default watchdog val)
+	 * after last reset
+	 */
+	if (time_before(jiffies, (adapter->last_reset_time + dev->watchdog_timeo))) {
+		netdev_dbg(dev, "Not yet time to tx timeout.\n");
+		return;
+	}
 	ibmvnic_reset(adapter, VNIC_RESET_TIMEOUT);
 }
 
@@ -2402,6 +2404,12 @@ restart_poll:
 
 		if (!pending_scrq(adapter, adapter->rx_scrq[scrq_num]))
 			break;
+		/* The queue entry at the current index is peeked at above
+		 * to determine that there is a valid descriptor awaiting
+		 * processing. We want to be sure that the current slot
+		 * holds a valid descriptor before reading its contents.
+		 */
+		dma_rmb();
 		next = ibmvnic_next_scrq(adapter, adapter->rx_scrq[scrq_num]);
 		rx_buff =
 		    (struct ibmvnic_rx_buff *)be64_to_cpu(next->
@@ -2860,15 +2868,26 @@ static int reset_one_sub_crq_queue(struct ibmvnic_adapter *adapter,
 {
 	int rc;
 
+	if (!scrq) {
+		netdev_dbg(adapter->netdev,
+			   "Invalid scrq reset. irq (%d) or msgs (%p).\n",
+			   scrq->irq, scrq->msgs);
+		return -EINVAL;
+	}
+
 	if (scrq->irq) {
 		free_irq(scrq->irq, scrq);
 		irq_dispose_mapping(scrq->irq);
 		scrq->irq = 0;
 	}
-
-	memset(scrq->msgs, 0, 4 * PAGE_SIZE);
-	atomic_set(&scrq->used, 0);
-	scrq->cur = 0;
+	if (scrq->msgs) {
+		memset(scrq->msgs, 0, 4 * PAGE_SIZE);
+		atomic_set(&scrq->used, 0);
+		scrq->cur = 0;
+	} else {
+		netdev_dbg(adapter->netdev, "Invalid scrq reset\n");
+		return -EINVAL;
+	}
 
 	rc = h_reg_sub_crq(adapter->vdev->unit_address, scrq->msg_token,
 			   4 * PAGE_SIZE, &scrq->crq_num, &scrq->hw_irq);
@@ -3100,13 +3119,18 @@ restart_loop:
 		unsigned int pool = scrq->pool_index;
 		int num_entries = 0;
 
+		/* The queue entry at the current index is peeked at above
+		 * to determine that there is a valid descriptor awaiting
+		 * processing. We want to be sure that the current slot
+		 * holds a valid descriptor before reading its contents.
+		 */
+		dma_rmb();
+
 		next = ibmvnic_next_scrq(adapter, scrq);
 		for (i = 0; i < next->tx_comp.num_comps; i++) {
-			if (next->tx_comp.rcs[i]) {
+			if (next->tx_comp.rcs[i])
 				dev_err(dev, "tx error %x\n",
 					next->tx_comp.rcs[i]);
-				continue;
-			}
 			index = be32_to_cpu(next->tx_comp.correlators[i]);
 			if (index & IBMVNIC_TSO_POOL_MASK) {
 				tx_pool = &adapter->tso_pool[pool];
@@ -3500,6 +3524,11 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *adapter,
 	}
 	spin_unlock_irqrestore(&scrq->lock, flags);
 
+	/* Ensure that the entire buffer descriptor has been
+	 * loaded before reading its contents
+	 */
+	dma_rmb();
+
 	return entry;
 }
 
@@ -3721,15 +3750,16 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
 	struct ibmvnic_login_buffer *login_buffer;
 	struct device *dev = &adapter->vdev->dev;
+	struct vnic_login_client_data *vlcd;
 	dma_addr_t rsp_buffer_token;
 	dma_addr_t buffer_token;
 	size_t rsp_buffer_size;
 	union ibmvnic_crq crq;
+	int client_data_len;
 	size_t buffer_size;
 	__be64 *tx_list_p;
 	__be64 *rx_list_p;
-	int client_data_len;
-	struct vnic_login_client_data *vlcd;
+	int rc;
 	int i;
 
 	if (!adapter->tx_scrq || !adapter->rx_scrq) {
@@ -3833,16 +3863,25 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	crq.login.cmd = LOGIN;
 	crq.login.ioba = cpu_to_be32(buffer_token);
 	crq.login.len = cpu_to_be32(buffer_size);
-	ibmvnic_send_crq(adapter, &crq);
+
+	adapter->login_pending = true;
+	rc = ibmvnic_send_crq(adapter, &crq);
+	if (rc) {
+		adapter->login_pending = false;
+		netdev_err(adapter->netdev, "Failed to send login, rc=%d\n", rc);
+		goto buf_rsp_map_failed;
+	}
 
 	return 0;
 
 buf_rsp_map_failed:
 	kfree(login_rsp_buffer);
+	adapter->login_rsp_buf = NULL;
 buf_rsp_alloc_failed:
 	dma_unmap_single(dev, buffer_token, buffer_size, DMA_TO_DEVICE);
 buf_map_failed:
 	kfree(login_buffer);
+	adapter->login_buf = NULL;
 buf_alloc_failed:
 	return -1;
 }
@@ -4385,6 +4424,15 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	u64 *size_array;
 	int i;
 
+	/* CHECK: Test/set of login_pending does not need to be atomic
+	 * because only ibmvnic_tasklet tests/clears this.
+	 */
+	if (!adapter->login_pending) {
+		netdev_warn(netdev, "Ignoring unexpected login response\n");
+		return 0;
+	}
+	adapter->login_pending = false;
+
 	dma_unmap_single(dev, adapter->login_buf_token, adapter->login_buf_sz,
 			 DMA_TO_DEVICE);
 	dma_unmap_single(dev, adapter->login_rsp_buf_token,
@@ -4414,7 +4462,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	     adapter->req_rx_add_queues !=
 	     be32_to_cpu(login_rsp->num_rxadd_subcrqs))) {
 		dev_err(dev, "FATAL: Inconsistent login and login rsp\n");
-		ibmvnic_remove(adapter->vdev);
+		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
 		return -EIO;
 	}
 	size_array = (u64 *)((u8 *)(adapter->login_rsp_buf) +
@@ -4756,6 +4804,11 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		case IBMVNIC_CRQ_INIT:
 			dev_info(dev, "Partner initialized\n");
 			adapter->from_passive_init = true;
+			/* Discard any stale login responses from prev reset.
+			 * CHECK: should we clear even on INIT_COMPLETE?
+			 */
+			adapter->login_pending = false;
+
 			if (!completion_done(&adapter->init_done)) {
 				complete(&adapter->init_done);
 				adapter->init_done_rc = -EIO;
@@ -5093,7 +5146,7 @@ map_failed:
 static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
 {
 	struct device *dev = &adapter->vdev->dev;
-	unsigned long timeout = msecs_to_jiffies(30000);
+	unsigned long timeout = msecs_to_jiffies(20000);
 	u64 old_num_rx_queues, old_num_tx_queues;
 	int rc;
 
@@ -5188,6 +5241,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	dev_set_drvdata(&dev->dev, netdev);
 	adapter->vdev = dev;
 	adapter->netdev = netdev;
+	adapter->login_pending = false;
 
 	ether_addr_copy(adapter->mac_addr, mac_addr_p);
 	ether_addr_copy(netdev->dev_addr, adapter->mac_addr);
@@ -5251,7 +5305,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	adapter->state = VNIC_PROBED;
 
 	adapter->wait_for_reset = false;
-
+	adapter->last_reset_time = jiffies;
 	return 0;
 
 ibmvnic_register_fail: